{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FDOJ6MONWFGQ7CXSLAMXR3XH3C","short_pith_number":"pith:FDOJ6MON","schema_version":"1.0","canonical_sha256":"28dc9f31cdb14d0f8af2581978eee7d8b2aa7a051f9d656bcb3540c43ad55b38","source":{"kind":"arxiv","id":"1911.01545","version":5},"attestation_state":"computed","paper":{"title":"Compositional Generalization with Tree Stack Memory Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Forough Arabshahi, Pranay Mundra, Sameer Singh, Zhichu Lu","submitted_at":"2019-11-05T00:27:03Z","abstract_excerpt":"We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent on compositional learning. We propose Tree Stack Memory Units (Tree-SMU) to enable strong compositional generalization. Tree-SMU is a recursive neural network with Stack Memory Units (\\SMU s), a novel memory augmented neural network whose memory has a differentiable stack structure. Each SMU in the tree architecture learns to read from its stack and to write to it by combining the stacks and states of its children th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1911.01545","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-05T00:27:03Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"ebf1b0bf97a9bad061fac55bd6315ea743d8ed1c6b18460df9443a83f1cad2ba","abstract_canon_sha256":"27d1df5fe9d0b78f77b8f33a907710a962acb73852fdd4baf2b96568e0b34324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:23.779881Z","signature_b64":"1fpThq94gNjLheG7tLxqkFnlrlIvL9ngj8tMXhyN3h4sYiFOJV1O/LURMM9tEEfgaw/Xaih2lEStID3K149XAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28dc9f31cdb14d0f8af2581978eee7d8b2aa7a051f9d656bcb3540c43ad55b38","last_reissued_at":"2026-07-05T01:43:23.779396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:23.779396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Compositional Generalization with Tree Stack Memory Units","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Animashree Anandkumar, Forough Arabshahi, Pranay Mundra, Sameer Singh, Zhichu Lu","submitted_at":"2019-11-05T00:27:03Z","abstract_excerpt":"We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent on compositional learning. We propose Tree Stack Memory Units (Tree-SMU) to enable strong compositional generalization. Tree-SMU is a recursive neural network with Stack Memory Units (\\SMU s), a novel memory augmented neural network whose memory has a differentiable stack structure. Each SMU in the tree architecture learns to read from its stack and to write to it by combining the stacks and states of its children th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.01545","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.01545/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1911.01545","created_at":"2026-07-05T01:43:23.779456+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.01545v5","created_at":"2026-07-05T01:43:23.779456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.01545","created_at":"2026-07-05T01:43:23.779456+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDOJ6MONWFGQ","created_at":"2026-07-05T01:43:23.779456+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDOJ6MONWFGQ7CXS","created_at":"2026-07-05T01:43:23.779456+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDOJ6MON","created_at":"2026-07-05T01:43:23.779456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C","json":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C.json","graph_json":"https://pith.science/api/pith-number/FDOJ6MONWFGQ7CXSLAMXR3XH3C/graph.json","events_json":"https://pith.science/api/pith-number/FDOJ6MONWFGQ7CXSLAMXR3XH3C/events.json","paper":"https://pith.science/paper/FDOJ6MON"},"agent_actions":{"view_html":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C","download_json":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C.json","view_paper":"https://pith.science/paper/FDOJ6MON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.01545&json=true","fetch_graph":"https://pith.science/api/pith-number/FDOJ6MONWFGQ7CXSLAMXR3XH3C/graph.json","fetch_events":"https://pith.science/api/pith-number/FDOJ6MONWFGQ7CXSLAMXR3XH3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C/action/storage_attestation","attest_author":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C/action/author_attestation","sign_citation":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C/action/citation_signature","submit_replication":"https://pith.science/pith/FDOJ6MONWFGQ7CXSLAMXR3XH3C/action/replication_record"}},"created_at":"2026-07-05T01:43:23.779456+00:00","updated_at":"2026-07-05T01:43:23.779456+00:00"}